Fixing most of the cppcheck errors. (#1142)

* fix cppcheck errors, first pass

* fix format

* fix returned value in examples

* add macro definitions for cppcheck

* fix the profile_gemm logic

* update the gemm profiler logic

* add more difinitions to cppcheck, fix couple more errors

* replace runtime error with message in device function

* fix a couple of int4 issues

* no return for fill function

* fix errors in data_types.hpp

* fix format

* fix few remaining errors

* fix errors in data_types.hpp

* fix last couple of errors in datat_types.hpp

[ROCm/composable_kernel commit: 180e572076]

library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp

@@ -265,6 +265,8 @@ struct ReferenceColumnToImage : public device::BaseOperator
 
                 return 0;
             }
+            throw std::runtime_error("Col2Img: number of dimensions should be between 1 and 3.");
+            return 1;
         }
 
         float Run(const device::BaseArgument* p_arg,

library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp

@@ -313,6 +313,9 @@ struct ReferenceConvBwdData : public device::BaseOperator
 
                 return 0;
             }
+            throw std::runtime_error(
+                "Conv_bwd_data: number of dimensions must be between 1 and 3.");
+            return 1;
         }
 
         float Run(const device::BaseArgument* p_arg,

library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp

@@ -265,6 +265,8 @@ struct ReferenceConvBwdWeight : public device::BaseOperator
 
                 return 0;
             }
+            throw std::runtime_error("Conv_bwd: number of dimensions must be between 1 and 3.");
+            return 1;
         }
 
         float Run(const device::BaseArgument* p_arg,

library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp

@@ -360,6 +360,8 @@ struct ReferenceConvFwd : public device::BaseOperator
 
                 return 0;
             }
+            throw std::runtime_error("Conv_fwd: number of dimensions must be between 1 and 3.");
+            return 1;
         }
 
         float Run(const device::BaseArgument* p_arg,

library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp

@@ -63,12 +63,11 @@ struct ReferenceGemm : public device::BaseOperator
                 const int K = arg.a_m_k_.mDesc.GetLengths()[1];
 
                 AccDataType v_acc = 0;
+                ComputeTypeA v_a  = 0;
+                ComputeTypeB v_b  = 0;
 
                 for(int k = 0; k < K; ++k)
                 {
-                    ComputeTypeA v_a;
-                    ComputeTypeB v_b;
-
                     // use PassThrough instead of ConvertBF16RTN for reference calculation
                     if constexpr(is_same_v<AElementwiseOperation,
                                            ck::tensor_operation::element_wise::ConvertBF16RTN>)
@@ -94,7 +93,7 @@ struct ReferenceGemm : public device::BaseOperator
                         ck::type_convert<AccDataType>(v_a) * ck::type_convert<AccDataType>(v_b);
                 }
 
-                CDataType v_c;
+                CDataType v_c = 0;
 
                 arg.c_element_op_(v_c, v_acc);
 

library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp

@@ -230,6 +230,8 @@ struct ReferenceImageToColumn : public device::BaseOperator
 
                 return 0;
             }
+            throw std::runtime_error("Img2Col: number of dimensions should be between 1 and 3.");
+            return 1;
         }
 
         float Run(const device::BaseArgument* p_arg,

library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp

@@ -106,9 +106,8 @@ struct DeviceOperationInstanceFactory<
         return op_ptrs;
     }
 };
-
+#endif
 } // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif

library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp

@@ -114,9 +114,8 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGemmSt
         return op_ptrs;
     }
 };
-
+#endif
 } // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck
-#endif